Whisper models with number tokens removed (for normalized recognition results). These models will recognize numbers as spoken words.
Darya Vozhdaeva
waveletdeboshir
AI & ML interests
Audio, ASR, TTS, DSP
Organizations
None yet
Collections
2
Pruned / trimmed versions of whisper models with unnecessary languages removed.
-
waveletdeboshir/whisper-small-ru-pruned
Automatic Speech Recognition • Updated • 112 -
waveletdeboshir/whisper-base-ru-pruned
Automatic Speech Recognition • Updated • 121 -
waveletdeboshir/whisper-tiny-ru-pruned
Automatic Speech Recognition • Updated • 90 -
waveletdeboshir/whisper-small-ru-pruned-ft
Automatic Speech Recognition • Updated • 67
models
7
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-large-v3-no-numbers
Automatic Speech Recognition
•
Updated
•
823
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-large-v3-turbo-no-numbers
Automatic Speech Recognition
•
Updated
•
145
•
2
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-small-ru-pruned-ft
Automatic Speech Recognition
•
Updated
•
67
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-base-ru-pruned
Automatic Speech Recognition
•
Updated
•
121
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-small-ru-pruned
Automatic Speech Recognition
•
Updated
•
112
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-tiny-ru-pruned
Automatic Speech Recognition
•
Updated
•
90
![](https://cdn-avatars.huggingface.co/v1/production/uploads/62de48df3af42b53b1cb763f/8zYwxnl8TefbYQute4dLz.jpeg)
waveletdeboshir/whisper-base-ru-pruned-ft
Automatic Speech Recognition
•
Updated
•
11
datasets
None public yet